# AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning

arXiv: https://arxiv.org/abs/2608.28312 · HTML: https://mlsanity.com/paper/2608.28312/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 27 of 27)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [PyHessian: Neural Networks Through the Lens of the Hessian](https://mlsanity.com/paper/1912.07145/) (2019)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Revisiting Natural Gradient for Deep Networks](https://mlsanity.com/paper/1301.3584/) (2013)
- [Variational Bayesian Unlearning](https://mlsanity.com/paper/2010.12883/) (2020)
- [Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench](https://mlsanity.com/paper/2410.22108/) (2024)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/2507.10485/) (2025)
- [On Large Language Model Continual Unlearning](https://mlsanity.com/paper/2407.10223/) (2024)
- [Remaining-data-free Machine Unlearning by Suppressing Sample Contribution](https://mlsanity.com/paper/2402.15109/) (2024)
- [SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders](https://mlsanity.com/paper/2503.14530/) (2025)
- [Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models](https://mlsanity.com/paper/2511.06793/) (2025)
- [Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification](https://mlsanity.com/paper/2412.16780/) (2024)
- [Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2511.20196/) (2025)
- [Gauss-Newton Unlearning for the LLM Era](https://mlsanity.com/paper/2602.10568/) (2026)
- [SineProject: Machine Unlearning for Stable Vision Language Alignment](https://mlsanity.com/paper/2511.18444/) (2025)
- [Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2601.22020/) (2026)
- [Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks](https://mlsanity.com/paper/2605.03759/) (2026)

## Built on by (most cited first, 1 of 1)

- [Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2608.30649/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) can memorize identity-specific facts about people in their fine-tuning data, creating privacy risks when a person requests deletion. Existing MLLM unlearning methods often assume access to retain images or ground-truth answers during deletion, which is unrealistic in many practical scenarios. We study identity unlearning when retain images are unavailable at deletion time. Our analysis shows that identity and visual-perception questions occupy distinct regions in fine-tuned hidden states and are organized differently: identity questions cluster by person, whereas perception questions cluster by question type. This suggests that identity knowledge can be suppressed without erasing general visual perception. Building on this observation, we propose AIM, a two-stage method that anchors an identity-forgetting target with a universal visual prompt and then matches the vision encoder to that target under a Fisher-based constraint. Extensive experiments show that AIM achieves competitive identity forgetting while preserving non-deleted identities, prior knowledge, and visual perception on the same images.